canvas-os is an AI agent skill, created by JarvisPC and published at openclaw/skills. ClawSecure audited canvas-os across 10 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 55/100 (Medium Risk). The 6 findings concentrate in Unauthorized Tool Use, Code Injection and Policy Violation, including Detects system manipulation, privilege escalation, and destructive file... and Detects system manipulation, privilege escalation, and destructive file.... 4 were rated high or critical severity.
Is canvas-os safe?
ClawSecure audited canvas-os and assigned a security score of 55/100 (Medium Risk), identifying 6 findings across Unauthorized Tool Use and Code Injection. Review the findings below before installing.
What did ClawSecure find in canvas-os?
ClawSecure identified 6 findings in canvas-os, concentrated in Unauthorized Tool Use, Code Injection and Policy Violation. 4 were rated high or critical severity. The most severe include Detects system manipulation, privilege escalation, and destructive file... and Detects system manipulation, privilege escalation, and destructive file....
How was canvas-os audited?
ClawSecure ran canvas-os through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 10 files from openclaw/skills.
What does a score of 55 mean?
ClawSecure assigned canvas-os a security score of 55/100, placing it in the Medium Risk range. This reflects 6 findings led by Unauthorized Tool Use that warrant review before production use. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).
Audit Findings for canvas-os
ClawSecure detected 6 security findings in canvas-os, spanning Unauthorized Tool Use, Code Injection, Policy Violation and Permissions Manifest.
- high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in
SKILL.md:85. - high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in
open-app.sh:18. - high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in
CANVAS-LOADING.md. - high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in
SKILL.md. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- info · Skill manifest does not include a 'license' field. Specifying a license.... Policy Violation finding detected in
SKILL.md.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for canvas-os
Eliminate dynamic code execution
Resolve policy violations
Add a config.json permissions manifest
Related Security Research
Why Generic Scanners Fail at AI Agent Security→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on February 7, 2026. canvas-os is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.